Impact of CT reconstruction algorithm on auto-segmentation performance.

Model-based iterative reconstruction (MBIR) reduces CT imaging dose while maintaining image quality. However, MBIR reduces noise while preserving edges which may impact intensity-based tasks such as auto-segmentation. This work evaluates the sensitivity of an auto-contouring prostate atlas across multiple MBIR reconstruction protocols and benchmarks the results against filtered back projection (FBP). Images were created from raw projection data for 11 prostate cancer cases using FBP and nine different MBIR reconstructions (3 protocols/3 noise reduction levels) yielding 10 reconstructions/patient. Five bony structures, bladder, rectum, prostate, and seminal vesicles (SVs) were segmented using an auto-segmentation pipeline that renders 3D binary masks for analysis. Performance was evaluated for volume percent difference (VPD) and Dice similarity coefficient (DSC), using FBP as the gold standard. Nonparametric Friedman tests plus post hoc all pairwise comparisons were employed to test for significant differences (P < 0.05) for soft tissue organs and protocol/level combinations. A physician performed qualitative grading of 396 MBIR contours across the prostate, bladder, SVs, and rectum in comparison to FBP using a six-point scale. MBIR contours agreed with FBP for bony anatomy (DSC ≥ 0.98), bladder (DSC ≥ 0.94, VPD < 8.5%), and prostate (DSC = 0.94 ± 0.03, VPD = 4.50 ± 4.77% (range: 0.07-26.39%). Increased variability was observed for rectum (VPD = 7.50 ± 7.56% and DSC = 0.90 ± 0.08) and SVs (VPD and DSC of 8.23 ± 9.86% range (0.00-35.80%) and 0.87 ± 0.11, respectively). Over the all protocol/level comparisons, a significant difference was observed for the prostate VPD between BSPL1 and BSTL2 (adjusted P-value = 0.039). Nevertheless, 300 of 396 (75.8%) of the four soft tissue structures using MBIR were graded as equivalent or better than FBP, suggesting that MBIR offered potential improvements in auto-segmentation performance when compared to FBP. Future work may involve tuning organ-specific MBIR parameters to further improve auto-segmentation performance. Running title: Impact of CT Reconstruction Algorithm on Auto-segmentation Performance.

A method for improving iodine contrast enhancement in abdominal computed tomography: experimental study in a pig model.

OBJECTIVES: To investigate the improvement in diagnostic image quality of an iodine contrast enhancement tool in an animal model for computed tomography (CT). METHODS: One pig was examined over several consecutive days with a CT system. The quantity of iodine as contrast medium (0.6-1.2 ml/kg) varied among different acquisitions. The contrast enhancement in the reconstructed slices was improved via a post-processing tool. The post-processing tool is an algorithm designed for enhancement of iodine contrast in CT data. Contrast-to-noise ratio (CNR), the detectability between soft-tissue and vascular structures, and quantitative image analysis were assessed. RESULTS: When reducing the quantity of contrast medium, our subjective image quality assessment revealed that it is visually possible to generate similar enhancement with less iodine. This observation was confirmed quantitatively in our CNR results. While employing the algorithm, the CNR between vascular structures and subcutaneous fat significantly improved. For unenhanced regions, we identified no change in HU values and no significant strengthening of artefacts. CONCLUSIONS: With post-processing there was a significantly improved diagnostic image quality compared with non-processed data. In particular, similar contrast enhancement could be achieved with a reduced quantity of contrast medium injected during the CT acquisition.

Prognostic Value of RCA Pericoronary Adipose Tissue CT-Attenuation Beyond High-Risk Plaques, Plaque Volume, and Ischemia.

OBJECTIVES: This study was designed to assess the prognostic value of pericoronary adipose tissue computed tomography attenuation (PCATa) beyond quantitative coronary computed tomography angiography (CCTA)-derived plaque volume and positron emission tomography (PET) determined ischemia. BACKGROUND: Inflammation plays a crucial role in atherosclerosis. PCATa has been shown to assess coronary-specific inflammation and is of prognostic value in patients with suspected coronary artery disease (CAD). METHODS: A total of 539 patients who underwent CCTA and [15O]H2O PET perfusion imaging because of suspected CAD were included. Imaging assessment included coronary artery calcium score (CACS), presence of obstructive CAD (≥50% stenosis) and high-risk plaques (HRPs), total plaque volume (TPV), calcified/noncalcified plaque volume (CPV/NCPV), PCATa, and myocardial ischemia. The endpoint was a composite of death and nonfatal myocardial infarction. Prognostic thresholds were determined for quantitative CCTA variables. RESULTS: During a median follow-up of 5.0 (interquartile range: 4.7 to 5.0) years, 33 events occurred. CACS >59 Agatston units, obstructive CAD, HRPs, TPV >220 mm3, CPV >110 mm3, NCPV >85 mm3, and myocardial ischemia were associated with shorter time to the endpoint with unadjusted hazard ratios (HRs) of 4.17 (95% confidence interval [CI]: 1.80 to 9.64), 4.88 (95% CI: 1.88 to 12.65), 3.41 (95% CI: 1.72 to 6.75), 7.91 (95% CI: 3.05 to 20.49), 5.82 (95% CI: 2.40 to 14.10), 8.07 (95% CI: 3.33 to 19.55), and 4.25 (95% CI: 1.84 to 9.78), respectively (p < 0.05 for all). Right coronary artery (RCA) PCATa above scanner specific thresholds was associated with worse prognosis (unadjusted HR: 2.84; 95% CI: 1.44 to 5.63; p = 0.003), whereas left anterior descending artery and circumflex artery PCATa were not related to outcome. RCA PCATa above scanner specific thresholds retained is prognostic value adjusted for imaging variables and clinical characteristics associated with the endpoint (adjusted HR: 2.45; 95% CI: 1.23 to 4.93; p = 0.011). CONCLUSIONS: Parameters associated with atherosclerotic burden and ischemia were more strongly associated with outcome than RCA PCATa. Nonetheless, RCA PCATa was of prognostic value beyond clinical characteristics, CACS, obstructive CAD, HRPs, TPV, CPV, NCPV, and ischemia.

Unsupervised abnormality detection through mixed structure regularization (MSR) in deep sparse autoencoders.

PURPOSE: The purpose of this study is to introduce and evaluate the mixed structure regularization (MSR) approach for a deep sparse autoencoder aimed at unsupervised abnormality detection in medical images. Unsupervised abnormality detection based on identifying outliers using deep sparse autoencoders is a very appealing approach for computer-aided detection systems as it requires only healthy data for training rather than expert annotated abnormality. However, regularization is required to avoid overfitting of the network to the training data. METHODS: We used coronary computed tomography angiography (CCTA) datasets of 90 subjects with expert annotated centerlines. We segmented coronary lumen and wall using an automatic algorithm with manual corrections where required. We defined normal coronary cross section as cross sections with a ratio between lumen and wall areas larger than 0.8. We divided the datasets into training, validation, and testing groups in a tenfold cross-validation scheme. We trained a deep sparse overcomplete autoencoder model for normality modeling with random structure and noise augmentation. We assessed the performance of our deep sparse autoencoder with MSR without denoising (SAE-MSR) and with denoising (SDAE-MSR) in comparison to deep sparse autoencoder (SAE), and deep sparse denoising autoencoder (SDAE) models in the task of detecting coronary artery disease from CCTA data on the test group. RESULTS: The SDAE-MSR achieved the best aggregated area under the curve (AUC) with a 20% improvement and the best aggregated Average Precision (AP) with a 30% improvement upon the SAE and SDAE (AUC: 0.78 to 0.94, AP: 0.66 to 0.86) in distinguishing between coronary cross sections with mild stenosis (stenosis grade < 0.3) and coronary cross sections with severe stenosis (stenosis grade > 0.7). The improvements were statistically significant (Mann-Whitney U-test, P < 0.001). Similarly, The SDAE-MSR achieved the best aggregated AUC (AP) with an 18% (18%) improvement upon the SAE and SDAE (AUC: 0.71 to 0.84, AP: 0.68 to 0.80). The improvements were statistically significant (Mann-Whitney U-test, P < 0.05). CONCLUSION: Deep sparse autoencoders with MSR in addition to explicit sparsity regularization term and stochastic corruption of the input data with Gaussian noise have the potential to improve unsupervised abnormality detection using deep-learning compared to common deep autoencoders.

Balanced Exploration and Exploitation Model search for efficient epipolar geometry estimation.

The estimation of the epipolar geometry is especially difficult when the putative correspondences include a low percentage of inlier correspondences and/or a large subset of the inliers is consistent with a degenerate configuration of the epipolar geometry that is totally incorrect. This work presents the Balanced Exploration and Exploitation Model Search (BEEM) algorithm that works very well especially for these difficult scenes. The algorithm handles these two problems in a unified manner. It includes the following main features: (1) Balanced use of three search techniques: global random exploration, local exploration near the current best solution and local exploitation to improve the quality of the model. (2) Exploits available prior information to accelerate the search process. (3) Uses the best found model to guide the search process, escape from degenerate models and to define an efficient stopping criterion. (4) Presents a simple and efficient method to estimate the epipolar geometry from two SIFT correspondences. (5) Uses the locality-sensitive hashing (LSH) approximate nearest neighbor algorithm for fast putative correspondences generation. The resulting algorithm when tested on real images with or without degenerate configurations gives quality estimations and achieves significant speedups compared to the state of the art algorithms.

A functionally personalized boundary condition model to improve estimates of fractional flow reserve with CT (CT-FFR).

PURPOSE: The purpose of this study is to develop and evaluate a functionally personalized boundary condition (BC) model for estimating the fractional flow reserve (FFR) from coronary computed tomography angiography (CCTA) using flow simulation (CT-FFR). MATERIALS AND METHODS: The CCTA data of 90 subjects with subsequent invasive FFR in 123 lesions within 21 days (range: 0-83) were retrospectively collected. We developed a functionally personalized BC model accounting specifically for the coronary microvascular resistance dependency on the coronary outlets pressure suggested by several physiological studies. We used the proposed model to estimate the hemodynamic significance of coronary lesions with an open-loop physics-based flow simulation. We generated three-dimensional (3D) coronary tree geometries using automatic software and corrected manually where required. We evaluated the improvement in CT-FFR estimates achieved using a functionally personalized BC model over anatomically personalized BC model using k-fold cross-validation. RESULTS: The functionally personalized BC model slightly improved CT-FFR specificity in determining hemodynamic significance of lesions with intermediate diameter stenosis (30%-70%, N = 72), compared to the anatomically personalized model lesions with invasive FFR measurements as the reference (sensitivity/specificity: 0.882/0.79 vs 0.882/0.763). For the entire set of 123 coronary lesions, the functionally personalized BC model improved only the area under the curve (AUC) but not the sensitivity/specificity in determining the hemodynamic significance of lesions, compared to the anatomically personalized model (AUC: 0.884 vs 0.875, sensitivity/specificity: 0.848/0.805). CONCLUSION: The functionally personalized BC model has the potential to improve the quality of CT-FFR estimates compared to an anatomically personalized BC model.

Improving CCTA-based lesions' hemodynamic significance assessment by accounting for partial volume modeling in automatic coronary lumen segmentation.

PURPOSE: The goal of this study was to assess the potential added benefit of accounting for partial volume effects (PVE) in an automatic coronary lumen segmentation algorithm that is used to determine the hemodynamic significance of a coronary artery stenosis from coronary computed tomography angiography (CCTA). MATERIALS AND METHODS: Two sets of data were used in our work: (a) multivendor CCTA datasets of 18 subjects from the MICCAI 2012 challenge with automatically generated centerlines and 3 reference segmentations of 78 coronary segments and (b) additional CCTA datasets of 97 subjects with 132 coronary lesions that had invasive reference standard FFR measurements. We extracted the coronary artery centerlines for the 97 datasets by an automated software program followed by manual correction if required. An automatic machine-learning-based algorithm segmented the coronary tree with and without accounting for the PVE. We obtained CCTA-based FFR measurements using a flow simulation in the coronary trees that were generated by the automatic algorithm with and without accounting for PVE. We assessed the potential added value of PVE integration as a part of the automatic coronary lumen segmentation algorithm by means of segmentation accuracy using the MICCAI 2012 challenge framework and by means of flow simulation overall accuracy, sensitivity, specificity, negative and positive predictive values, and the receiver operated characteristic (ROC) area under the curve. We also evaluated the potential benefit of accounting for PVE in automatic segmentation for flow simulation for lesions that were diagnosed as obstructive based on CCTA which could have indicated a need for an invasive exam and revascularization. RESULTS: Our segmentation algorithm improves the maximal surface distance error by ~39% compared to previously published method on the 18 datasets from the MICCAI 2012 challenge with comparable Dice and mean surface distance. Results with and without accounting for PVE were comparable. In contrast, integrating PVE analysis into an automatic coronary lumen segmentation algorithm improved the flow simulation specificity from 0.6 to 0.68 with the same sensitivity of 0.83. Also, accounting for PVE improved the area under the ROC curve for detecting hemodynamically significant CAD from 0.76 to 0.8 compared to automatic segmentation without PVE analysis with invasive FFR threshold of 0.8 as the reference standard. Accounting for PVE in flow simulation to support the detection of hemodynamic significant disease in CCTA-based obstructive lesions improved specificity from 0.51 to 0.73 with same sensitivity of 0.83 and the area under the curve from 0.69 to 0.79. The improvement in the AUC was statistically significant (N = 76, Delong's test, P = 0.012). CONCLUSION: Accounting for the partial volume effects in automatic coronary lumen segmentation algorithms has the potential to improve the accuracy of CCTA-based hemodynamic assessment of coronary artery lesions.

Virtual nonenhanced abdominal dual-energy MDCT: Analysis of image characteristics.

AIM: To evaluate abdominal and pelvic image characteristics and artifacts on virtual nonenhanced (VNE) images generated from contrast-enhanced dual-energy multidetector computed tomography (MDCT) studies. METHODS: Hadassah-Hebrew University Medical Institutional Review Board approval was obtained; 22 patients underwent clinically-indicated abdominal and pelvic single-source dual-energy MDCT (Philips Healthcare, Cleveland, OH, USA), pre- and post-IV administration of Omnipaque 300 contrast (100 cc). Various solid and vascular structures were evaluated. VNE images were generated from the portal contrast-enhanced phase using probabilistic separation. Contrast-enhanced-, regular nonenhanced (RNE)-, and VNE images were evaluated with a total of 1494 density measurements. The ratio of iodine contrast deletion was calculated. Visualization of calcifications, urinary tract stones, and image artifacts in VNE images were assessed. RESULTS: VNE images were successfully generated in all patients. Significant portal-phase iodine contrast deletion was seen in the kidney (61.7%), adrenal gland (55.3%), iliac artery (55.0%), aorta (51.6%), and spleen (34.5%). Contrast deletion was also significant in the right atrium (RA) (51.5%) and portal vein (39.3%), but insignificant in the iliac vein and inferior vena cava (IVC). Average post contrast-to-VNE HU differences were significant (P < 0.05) in the: RA -135.3 (SD 121.8), aorta -114.1 (SD 48.5), iliac artery -104.6 (SD 53.7), kidney -30.3 (SD 34.9), spleen -9.2 (SD 8.8), and portal vein -7.7 (SD 13.2). Average VNE-to-RNE HU differences were significant in all organs but the prostate and subcutaneous fat: aorta 38.0 (SD 9.3), RA 37.8 (SD 16.1), portal vein 21.8 (SD 12.0), IVC 12.2 (SD 11.6), muscle 3.3 (SD 4.9), liver 5.7 (SD 6.4), spleen 22.3 (SD 9.8), kidney 40.5 (SD 6.8), and adrenal 20.7 (SD 13.5). On VNE images, 196/213 calcifications (92%) and 5/6 renal stones (84%) were visualized. Lytic-like artifacts in the vertebral bodies were seen in all studies. CONCLUSION: Iodine deletion in VNE images is most significant in arteries, and less significant in solid organs and veins. Most vascular and intra-abdominal organ calcifications are preserved.